Abstract
The Adaptive Resonance Theory (ART) model is one of the triumphs of modern neural network theory developed to overcome the stability-plasticity dilemma [1], [2], [37], [38], [47]. When someone has to add more to what they have already learnt, there is no need for complete retraining as there is no chance of one forgetting all that he has already learnt. But such is not the case in electronic networks as a catastrophic forgetting may occur if one tries to add more patterns to a stable trained network. There is a trade-off between the stability and ability to learn new data. This is known as the stability plasticity dilemma.
An Erratum can be found at http://dx.doi.org/10.1007/978-3-540-85130-1_11
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
David, V.K., Rajasekaran, S. (2009). Retracted Chapter: Adaptive Resonance Theory Networks. In: Pattern Recognition using Neural and Functional Networks. Studies in Computational Intelligence, vol 160. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-85130-1_4
Download citation
DOI: https://doi.org/10.1007/978-3-540-85130-1_4
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-85129-5
Online ISBN: 978-3-540-85130-1
eBook Packages: EngineeringEngineering (R0)